{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z2UJLEPKYLEHJDMPDSD7XIPK7F","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0eacb855d1ab9cde24e340399e1daa1542f0a087121e76b368810b463e210474","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T06:10:38Z","title_canon_sha256":"0d8b34748e7e4aebd25aa3fbffbbe06ed793de12adf83073887b7fe2a830d623"},"schema_version":"1.0","source":{"id":"2606.01039","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01039","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01039v1","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01039","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"Z2UJLEPKYLEH","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"pith_short_16","alias_value":"Z2UJLEPKYLEHJDMP","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"pith_short_8","alias_value":"Z2UJLEPK","created_at":"2026-06-02T01:04:19Z"}],"graph_snapshots":[{"event_id":"sha256:124fb2773c84c02a697348f91ed47baf57e6e0a805b03895ca096b085d249e80","target":"graph","created_at":"2026-06-02T01:04:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.01039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) is a widely used technique to transfer capabilities from capable teacher language models to the base student models, and can be formulated in a reinforcement learning style objective using student generated rollouts. Yet, despite the divergence reward being dependent on student model likelihood, existing works usually adopt a stop gradient design primarily for stability, which makes the resulting advantage estimation questionable. In this work, we provide a generic optimization framework based on f-divergence between the student and teacher, and mathematically revi","authors_text":"David Yao, Genta Indra Winata, Han Lin, Hanyang Zhao, Haoxian Chen, Wenpin Tang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T06:10:38Z","title":"OPD+: Rethinking the Advantage Design for On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01039","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:823b6e9eac985ed52c1dad7e6a7456a10cfc6f9da3a7673c1f2c2faf7be1a4b8","target":"record","created_at":"2026-06-02T01:04:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0eacb855d1ab9cde24e340399e1daa1542f0a087121e76b368810b463e210474","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T06:10:38Z","title_canon_sha256":"0d8b34748e7e4aebd25aa3fbffbbe06ed793de12adf83073887b7fe2a830d623"},"schema_version":"1.0","source":{"id":"2606.01039","kind":"arxiv","version":1}},"canonical_sha256":"cea89591eac2c8748d8f1c87fba1eaf95af5f0a1e3c4085271790e92285b5496","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cea89591eac2c8748d8f1c87fba1eaf95af5f0a1e3c4085271790e92285b5496","first_computed_at":"2026-06-02T01:04:19.241853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:19.241853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hgp8tRw9n3E7bZWQrrv0NpIWUaA9AWkDLI9+OOeeSl7GfrwiSjuiU2iHmWjByZmXy0QxyGXpse4mYsUddzoMAA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:19.242296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01039","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:823b6e9eac985ed52c1dad7e6a7456a10cfc6f9da3a7673c1f2c2faf7be1a4b8","sha256:124fb2773c84c02a697348f91ed47baf57e6e0a805b03895ca096b085d249e80"],"state_sha256":"7dd182ec2a5d781a80ff410bf467055def3e6aa4b6516f00d6e41bd5cd1259e9"}